Instructions to use usermma/NEXUS-Coder-Abliterated-mlx-5Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use usermma/NEXUS-Coder-Abliterated-mlx-5Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir NEXUS-Coder-Abliterated-mlx-5Bit usermma/NEXUS-Coder-Abliterated-mlx-5Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
metadata
language: en
tags:
- obliteratus
- abliteration
- uncensored
- obliterate
- mlx
- mlx-my-repo
base_model: usermma/NEXUS-Coder-Abliterated
usermma/NEXUS-Coder-Abliterated-mlx-5Bit
The Model usermma/NEXUS-Coder-Abliterated-mlx-5Bit was converted to MLX format from usermma/NEXUS-Coder-Abliterated using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("usermma/NEXUS-Coder-Abliterated-mlx-5Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)